[PATCH v6 4/6] dmabuf: Add gpu cgroup charge transfer function

From: "T.J. Mercier" <tjmercier@google.com>
To: tjmercier@google.com, "Sumit Semwal" <sumit.semwal@linaro.org>,
	"Christian König" <christian.koenig@amd.com>,
	"Tejun Heo" <tj@kernel.org>, "Zefan Li" <lizefan.x@bytedance.com>,
	"Johannes Weiner" <hannes@cmpxchg.org>
Cc: kernel-team@android.com, tkjos@android.com, Kenny.Ho@amd.com,
	cgroups@vger.kernel.org, skhan@linuxfoundation.org,
	cmllamas@google.com, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, linaro-mm-sig@lists.linaro.org,
	jstultz@google.com, kaleshsingh@google.com, hridya@google.com,
	mkoutny@suse.com, surenb@google.com, linux-media@vger.kernel.org
Subject: [PATCH v6 4/6] dmabuf: Add gpu cgroup charge transfer function
Date: Mon,  2 May 2022 23:19:38 +0000	[thread overview]
Message-ID: <20220502231944.3891435-5-tjmercier@google.com> (raw)
In-Reply-To: <20220502231944.3891435-1-tjmercier@google.com>

The dma_buf_transfer_charge function provides a way for processes to
transfer charge of a buffer to a different process. This is essential
for the cases where a central allocator process does allocations for
various subsystems, hands over the fd to the client who requested the
memory and drops all references to the allocated memory.

Originally-by: Hridya Valsaraju <hridya@google.com>
Signed-off-by: T.J. Mercier <tjmercier@google.com>

---
v5 changes
Fix commit message which still contained the old name for
dma_buf_transfer_charge per Michal Koutný.

Modify the dma_buf_transfer_charge API to accept a task_struct instead
of a gpucg. This avoids requiring the caller to manage the refcount
of the gpucg upon failure and confusing ownership transfer logic.

v4 changes
Adjust ordering of charge/uncharge during transfer to avoid potentially
hitting cgroup limit per Michal Koutný.

v3 changes
Use more common dual author commit message format per John Stultz.

v2 changes
Move dma-buf cgroup charge transfer from a dma_buf_op defined by every
heap to a single dma-buf function for all heaps per Daniel Vetter and
Christian König.
---
 drivers/dma-buf/dma-buf.c  | 57 +++++++++++++++++++++++++++++++++++
 include/linux/cgroup_gpu.h | 14 +++++++++
 include/linux/dma-buf.h    |  6 ++++
 kernel/cgroup/gpu.c        | 62 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 139 insertions(+)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index bc89c44bd9b9..f3fb844925e2 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1341,6 +1341,63 @@ void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map)
 }
 EXPORT_SYMBOL_NS_GPL(dma_buf_vunmap, DMA_BUF);
 
+/**
+ * dma_buf_transfer_charge - Change the GPU cgroup to which the provided dma_buf is charged.
+ * @dmabuf:	[in]	buffer whose charge will be migrated to a different GPU cgroup
+ * @target:	[in]	the task_struct of the destination process for the GPU cgroup charge
+ *
+ * Only tasks that belong to the same cgroup the buffer is currently charged to
+ * may call this function, otherwise it will return -EPERM.
+ *
+ * Returns 0 on success, or a negative errno code otherwise.
+ */
+int dma_buf_transfer_charge(struct dma_buf *dmabuf, struct task_struct *target)
+{
+	struct gpucg *current_gpucg, *target_gpucg, *to_release;
+	int ret;
+
+	if (!dmabuf->gpucg || !dmabuf->gpucg_bucket) {
+		/* This dmabuf is not tracked under GPU cgroup accounting */
+		return 0;
+	}
+
+	current_gpucg = gpucg_get(current);
+	target_gpucg = gpucg_get(target);
+	to_release = target_gpucg;
+
+	/* If the source and destination cgroups are the same, don't do anything. */
+	if (current_gpucg == target_gpucg) {
+		ret = 0;
+		goto skip_transfer;
+	}
+
+	/*
+	 * Verify that the cgroup of the process requesting the transfer
+	 * is the same as the one the buffer is currently charged to.
+	 */
+	mutex_lock(&dmabuf->lock);
+	if (current_gpucg != dmabuf->gpucg) {
+		ret = -EPERM;
+		goto err;
+	}
+
+	ret = gpucg_transfer_charge(
+		dmabuf->gpucg, target_gpucg, dmabuf->gpucg_bucket, dmabuf->size);
+	if (ret)
+		goto err;
+
+	to_release = dmabuf->gpucg;
+	dmabuf->gpucg = target_gpucg;
+
+err:
+	mutex_unlock(&dmabuf->lock);
+skip_transfer:
+	gpucg_put(current_gpucg);
+	gpucg_put(to_release);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(dma_buf_transfer_charge, DMA_BUF);
+
 #ifdef CONFIG_DEBUG_FS
 static int dma_buf_debug_show(struct seq_file *s, void *unused)
 {
diff --git a/include/linux/cgroup_gpu.h b/include/linux/cgroup_gpu.h
index 4dfe633d6ec7..f5973ef9f926 100644
--- a/include/linux/cgroup_gpu.h
+++ b/include/linux/cgroup_gpu.h
@@ -83,7 +83,13 @@ static inline struct gpucg *gpucg_parent(struct gpucg *cg)
 }
 
 int gpucg_charge(struct gpucg *gpucg, struct gpucg_bucket *bucket, u64 size);
+
 void gpucg_uncharge(struct gpucg *gpucg, struct gpucg_bucket *bucket, u64 size);
+
+int gpucg_transfer_charge(struct gpucg *source,
+			  struct gpucg *dest,
+			  struct gpucg_bucket *bucket,
+			  u64 size);
 int gpucg_register_bucket(struct gpucg_bucket *bucket, const char *name);
 #else /* CONFIG_CGROUP_GPU */
 
@@ -118,6 +124,14 @@ static inline void gpucg_uncharge(struct gpucg *gpucg,
 				  struct gpucg_bucket *bucket,
 				  u64 size) {}
 
+static inline int gpucg_transfer_charge(struct gpucg *source,
+					struct gpucg *dest,
+					struct gpucg_bucket *bucket,
+					u64 size)
+{
+	return 0;
+}
+
 static inline int gpucg_register_bucket(struct gpucg_bucket *bucket, const char *name) {}
 #endif /* CONFIG_CGROUP_GPU */
 #endif /* _CGROUP_GPU_H */
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 8e7c55c830b3..438ad8577b76 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -18,6 +18,7 @@
 #include <linux/file.h>
 #include <linux/err.h>
 #include <linux/scatterlist.h>
+#include <linux/sched.h>
 #include <linux/list.h>
 #include <linux/dma-mapping.h>
 #include <linux/fs.h>
@@ -650,9 +651,14 @@ void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map);
 void dma_buf_exp_info_set_gpucg(struct dma_buf_export_info *exp_info,
 				struct gpucg *gpucg,
 				struct gpucg_bucket *gpucg_bucket);
+
+int dma_buf_transfer_charge(struct dma_buf *dmabuf, struct task_struct *target);
 #else/* CONFIG_CGROUP_GPU */
 static inline void dma_buf_exp_info_set_gpucg(struct dma_buf_export_info *exp_info,
 					      struct gpucg *gpucg,
 					      struct gpucg_bucket *gpucg_bucket) {}
+
+static inline int dma_buf_transfer_charge(struct dma_buf *dmabuf, struct task_struct *target)
+{ return 0; }
 #endif /* CONFIG_CGROUP_GPU */
 #endif /* __DMA_BUF_H__ */
diff --git a/kernel/cgroup/gpu.c b/kernel/cgroup/gpu.c
index 34d0a5b85834..7dfbe0fd7e45 100644
--- a/kernel/cgroup/gpu.c
+++ b/kernel/cgroup/gpu.c
@@ -252,6 +252,68 @@ void gpucg_uncharge(struct gpucg *gpucg, struct gpucg_bucket *bucket, u64 size)
 	css_put(&gpucg->css);
 }
 
+/**
+ * gpucg_transfer_charge - Transfer a GPU charge from one cgroup to another.
+ *
+ * @source:	[in]	The GPU cgroup the charge will be transferred from.
+ * @dest:	[in]	The GPU cgroup the charge will be transferred to.
+ * @bucket:	[in]	The GPU cgroup bucket corresponding to the charge.
+ * @size:	[in]	The size of the memory in bytes.
+ *                      This size will be rounded up to the nearest page size.
+ *
+ * Returns 0 on success, or a negative errno code otherwise.
+ */
+int gpucg_transfer_charge(struct gpucg *source,
+			  struct gpucg *dest,
+			  struct gpucg_bucket *bucket,
+			  u64 size)
+{
+	struct page_counter *counter;
+	u64 nr_pages;
+	struct gpucg_resource_pool *rp_source, *rp_dest;
+	int ret = 0;
+
+	nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	mutex_lock(&gpucg_mutex);
+	rp_source = cg_rpool_find_locked(source, bucket);
+	if (unlikely(!rp_source)) {
+		ret = -ENOENT;
+		goto exit_early;
+	}
+
+	rp_dest = cg_rpool_get_locked(dest, bucket);
+	if (IS_ERR(rp_dest)) {
+		ret = PTR_ERR(rp_dest);
+		goto exit_early;
+	}
+
+	/*
+	 * First uncharge from the pool it's currently charged to. This ordering avoids double
+	 * charging while the transfer is in progress, which could cause us to hit a limit.
+	 * If the try_charge fails for this transfer, we need to be able to reverse this uncharge,
+	 * so we continue to hold the gpucg_mutex here.
+	 */
+	page_counter_uncharge(&rp_source->total, nr_pages);
+	css_put(&source->css);
+
+	/* Now attempt the new charge */
+	if (page_counter_try_charge(&rp_dest->total, nr_pages, &counter)) {
+		css_get(&dest->css);
+	} else {
+		/*
+		 * The new charge failed, so reverse the uncharge from above. This should always
+		 * succeed since charges on source are blocked by gpucg_mutex.
+		 */
+		WARN_ON(!page_counter_try_charge(&rp_source->total, nr_pages, &counter));
+		css_get(&source->css);
+		ret = -ENOMEM;
+	}
+exit_early:
+	mutex_unlock(&gpucg_mutex);
+	return ret;
+}
+
 /**
  * gpucg_register_bucket - Registers a bucket for memory accounting using the
  * GPU cgroup controller.
-- 
2.36.0.464.gb9c8b46e94-goog

